Upload Date | September 06 2024 10:37 AM |
Views | 3 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi 23124RN87C |
Model ID | Xiaomi 23124RN87C |
Motherboard | air |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.20 GHz |
Memory Information | |
---|---|
Size | 5.46 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
173
32.3 IPS |
|
Image Classification (F16)
|
100% |
178
33.4 IPS |
|
Image Classification (I8)
|
97% |
327
61.1 IPS |
|
Image Segmentation (F32)
|
100% |
282
4.71 IPS |
|
Image Segmentation (F16)
|
100% |
281
4.69 IPS |
|
Image Segmentation (I8)
|
98% |
407
6.80 IPS |
|
Pose Estimation (F32)
|
100% |
396
0.48 IPS |
|
Pose Estimation (F16)
|
100% |
386
0.47 IPS |
|
Pose Estimation (I8)
|
100% |
1774
2.15 IPS |
|
Object Detection (F32)
|
100% |
220
16.4 IPS |
|
Object Detection (F16)
|
100% |
215
16.1 IPS |
|
Object Detection (I8)
|
61% |
409
30.6 IPS |
|
Face Detection (F32)
|
100% |
417
4.96 IPS |
|
Face Detection (F16)
|
100% |
427
5.08 IPS |
|
Face Detection (I8)
|
86% |
855
10.2 IPS |
|
Depth Estimation (F32)
|
100% |
409
3.17 IPS |
|
Depth Estimation (F16)
|
100% |
411
3.19 IPS |
|
Depth Estimation (I8)
|
95% |
880
6.83 IPS |
|
Style Transfer (F32)
|
100% |
642
0.84 IPS |
|
Style Transfer (F16)
|
100% |
641
0.84 IPS |
|
Style Transfer (I8)
|
98% |
1883
2.48 IPS |
|
Image Super-Resolution (F32)
|
100% |
214
7.65 IPS |
|
Image Super-Resolution (F16)
|
100% |
213
7.62 IPS |
|
Image Super-Resolution (I8)
|
98% |
633
22.6 IPS |
|
Text Classification (F32)
|
100% |
197
283.4 IPS |
|
Text Classification (F16)
|
100% |
213
306.7 IPS |
|
Text Classification (I8)
|
92% |
181
259.5 IPS |
|
Machine Translation (F32)
|
100% |
381
7.02 IPS |
|
Machine Translation (F16)
|
100% |
390
7.19 IPS |
|
Machine Translation (I8)
|
64% |
257
4.73 IPS |